Folgen
Xinmeng Huang
Xinmeng Huang
Bestätigte E-Mail-Adresse bei sas.upenn.edu
Titel
Zitiert von
Zitiert von
Jahr
DecentLaM: Decentralized momentum SGD for large-batch deep training
K Yuan, Y Chen, X Huang, Y Zhang, P Pan, Y Xu, W Yin
CVF International Conference on Computer Vision (ICCV), 3009-3019, 2021
572021
Removing data heterogeneity influence enhances network topology dependence of decentralized sgd
K Yuan, SA Alghunaim, X Huang
Journal of Machine Learning Research 24 (280), 1-53, 2023
362023
Lower bounds and nearly optimal algorithms in distributed learning with communication compression
X Huang, Y Chen, W Yin, K Yuan
Advances in Neural Information Processing Systems 35, 18955-18969, 2022
252022
Tight Coefficients of Averaged Operators via Scaled Relative Graph
X Huang, EK Ryu, W Yin
Journal of Mathematical Analysis and Applications 490 (1), 124211, 2020
232020
T-cal: An optimal test for the calibration of predictive models
D Lee, X Huang, H Hassani, E Dobriban
Journal of Machine Learning Research 24 (335), 1-72, 2023
222023
Stochastic controlled averaging for federated learning with communication compression
X Huang, P Li, X Li
International Conference on Learning Representations (ICLR 2024), 2023
212023
Revisiting optimal convergence rate for smooth and non-convex stochastic decentralized optimization
K Yuan, X Huang, Y Chen, X Zhang, Y Zhang, P Pan
Advances in Neural Information Processing Systems 35, 36382-36395, 2022
212022
Recent advances in artificial intelligence boosting materials design for electrochemical energy storage
X Liu, K Fan, X Huang, J Ge, Y Liu, H Kang
Chemical Engineering Journal, 151625, 2024
192024
Momentum benefits non-iid federated learning simply and provably
Z Cheng, X Huang, K Yuan
International Conference on Learning Representations (ICLR 2024), 2023
182023
An improved analysis and rates for variance reduction under without-replacement sampling orders
X Huang, K Yuan, X Mao, W Yin
Advances in Neural Information Processing Systems 34, 3232-3243, 2021
162021
Demystifying disagreement-on-the-line in high dimensions
D Lee, B Moniri, X Huang, E Dobriban, H Hassani
International Conference on Machine Learning, 19053-19093, 2023
132023
Uncertainty in language models: Assessment through rank-calibration
X Huang, S Li, M Yu, M Sesia, H Hassani, I Lee, O Bastani, E Dobriban
arXiv preprint arXiv:2404.03163, 2024
122024
Scaled Relative Graph of Normal Matrices
X Huang, EK Ryu, W Yin
arXiv preprint arXiv:2001.02061, 2019
112019
Collaborative learning of discrete distributions under heterogeneity and communication constraints
X Huang, D Lee, E Dobriban, H Hassani
Advances in neural information processing systems 35, 31915-31928, 2022
72022
Unbiased compression saves communication in distributed optimization: when and how much?
Y He, X Huang, K Yuan
Advances in Neural Information Processing Systems 36, 2024
62024
Decentralized Bilevel Optimization over Graphs: Loopless Algorithmic Update and Transient Iteration Complexity
B Kong, S Zhu, S Lu, X Huang, K Yuan
arXiv preprint arXiv:2402.03167, 2024
62024
Optimal complexity in non-convex decentralized learning over time-varying networks
X Huang, K Yuan
arXiv preprint arXiv:2211.00533, 2022
62022
Lower bounds and accelerated algorithms in distributed stochastic optimization with communication compression
Y He, X Huang, Y Chen, W Yin, K Yuan
arXiv preprint arXiv:2305.07612, 2023
52023
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
X Huang, S Li, E Dobriban, O Bastani, H Hassani, D Ding
arXiv preprint arXiv:2405.19544, 2024
32024
Optimal multitask linear regression and contextual bandits under sparse heterogeneity
X Huang, K Xu, D Lee, H Hassani, H Bastani, E Dobriban
Journal of the American Statistical Association, 1-26, 2024
2*2024
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20